CN109035685B - High-altitude falling prevention system and method for infants - Google Patents

High-altitude falling prevention system and method for infants Download PDF

Info

Publication number
CN109035685B
CN109035685B CN201810665581.9A CN201810665581A CN109035685B CN 109035685 B CN109035685 B CN 109035685B CN 201810665581 A CN201810665581 A CN 201810665581A CN 109035685 B CN109035685 B CN 109035685B
Authority
CN
China
Prior art keywords
infant
module
target object
acceleration
pin
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810665581.9A
Other languages
Chinese (zh)
Other versions
CN109035685A (en
Inventor
刘半藤
周煊勇
金合丽
陈友荣
王章权
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Shuren University
Original Assignee
Zhejiang Shuren University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Shuren University filed Critical Zhejiang Shuren University
Priority to CN201810665581.9A priority Critical patent/CN109035685B/en
Publication of CN109035685A publication Critical patent/CN109035685A/en
Application granted granted Critical
Publication of CN109035685B publication Critical patent/CN109035685B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
    • G08B21/0233—System arrangements with pre-alarms, e.g. when a first distance is exceeded
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
    • G08B21/0272—System arrangements wherein the object is to detect exact location of child or item using triangulation other than GPS
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
    • G08B21/028—Communication between parent and child units via remote transmission means, e.g. satellite network
    • G08B21/0283—Communication between parent and child units via remote transmission means, e.g. satellite network via a telephone network, e.g. cellular GSM

Landscapes

  • Health & Medical Sciences (AREA)
  • Child & Adolescent Psychology (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Emergency Alarm Devices (AREA)

Abstract

The invention relates to a high-altitude falling prevention system and method for infants. The invention adopts a data acquisition subsystem to capture the face, acquire the face information, the height and the position information of the human body, and send the acquired information to an ARM control subsystem for processing, if the face of the infant is detected, the motion trend of the infant is predicted by further utilizing a motion state prediction algorithm of Kalman filtering, if the infant is predicted to be dangerous, an alarm and emergency measure device is triggered, and the alarm information is sent to a mobile phone terminal. Compared with the traditional high-altitude anti-falling system and method, the invention reduces the detection blind area, improves the child recognition rate, reduces the false alarm rate and has higher application value.

Description

High-altitude falling prevention system and method for infants
Technical Field
The invention relates to the technical field of data processing, in particular to a high-altitude falling prevention system and method for infants.
Background
Nowadays, with the continuous development of urbanization process, urban population is more and more, and in order to ensure the population accommodation capacity of the city, a large number of high-rise residences are built in the city, but more and more high-altitude falling accidents are caused, especially the accidents that children climb windows and fall from the high-rise residences, which are layered in the reports of media and social platforms, cause huge loss and trauma to the society and families. At present, due to the limitation of high-altitude buildings, extra high-altitude protection facilities are not allowed to be built on the outer vertical surface, so that an indoor high-altitude anti-falling system for infants is urgently needed to protect the infants from falling from the building and reduce the accident rate of the infants from falling from the building.
At present, the indoor high-altitude infant falling prevention system is immature in application and has no related commodity in the market. The main research results also focus on theory and design stages, wherein most of the children are detected by a single sensor, the defects of detection blind areas, wrong identification of the children and high false alarm rate exist, and the current design lacks the function of identifying the movement trend of the children, so that the children cannot be predicted whether to approach a window in advance, and the time of system response is insufficient and unnecessary false alarm is caused. Therefore, there is a need for a high-altitude anti-falling system for infants, which can accurately identify infants, predict the movement trend of infants in advance, and take effective emergency measures.
Disclosure of Invention
In order to solve the problems of a detection blind area, infant identification errors and high false alarm rate of a traditional detection method, the invention provides an infant high-altitude anti-falling system based on camera, infrared and ultrasonic data fusion, a wide-angle camera is added to capture a face of an infant and reduce the detection blind area, the identity of the infant is identified through a face identification technology, the infant identification error rate is reduced, a motion state prediction algorithm of Kalman filtering is provided to estimate the current motion track of the infant, the false alarm rate is reduced, if the infant is detected to be possible to have an accident, the alarm information is sent to an infant guardian through WiFi and 4G wireless communication, and meanwhile, an alarm sound is sent and a window is closed to prevent the accident.
In order to achieve the above object, the present invention has the following configurations:
this infant high altitude system of preventing falling includes data acquisition subsystem, ARM control subsystem and cell-phone terminal, the data acquisition subsystem includes:
the camera module is used for acquiring a face image of a target object;
the infrared human body sensing module is used for measuring the height of a target object;
the ultrasonic module is used for positioning a target object;
the ARM control subsystem comprises:
the GPIO module is used for reading the data of the infrared human body induction module and the data of the ultrasonic wave module;
the camera interface module is used for reading the face image data collected by the camera module;
the WIFI module is used for communicating with the mobile phone terminal;
the ARM module is connected with the GPIO module, the camera interface module and the WIFI module;
the ARM module analyzes the face image data and the height data of the target object to judge whether an infant is detected;
if the infant is detected, the ARM module judges whether the target object enters a dangerous area or not according to the positioning data of the target object, and when the target object enters the dangerous area, the alarming information is sent to the mobile phone terminal through the WIFI module.
Optionally, the ARM control subsystem further comprises a window closing brake, the window closing brake is installed at the middle position of the lower edge of the window, and when the ARM module judges that the infant enters the dangerous area, the window is controlled to be closed through the window closing controller.
Optionally, the ARM control subsystem further comprises an alarm module, and when the ARM module judges that the infant enters a dangerous area, the alarm module is controlled to perform sound alarm and/or light alarm.
The embodiment of the invention also provides a high-altitude anti-falling method for the infant, which adopts the high-altitude anti-falling system for the infant and comprises the following steps:
the ARM module analyzes the face image data and the height data of the target object to judge whether an infant is detected;
if the infant is detected, the ARM module judges whether the target object enters a dangerous area or not according to the positioning data of the target object, and when the target object enters the dangerous area, the alarming information is sent to the mobile phone terminal through the WIFI module.
Optionally, the ARM module analyzes the face image data and the height data of the target object to determine whether an infant is detected, including the following steps:
the ARM module analyzes the face image data and judges whether the age of the target object is within a preset age range;
the ARM module analyzes the height area of the target object and judges whether the height of the target object is within a preset height range or not;
and if the age of the target object is within the preset age range and the height of the target object is within the preset height range, judging that the infant is detected.
Optionally, the ARM module determines whether the target object enters a dangerous area according to the positioning data of the target object, including the following steps:
the ARM module calculates the acceleration of the infant according to the positioning data of the target object, predicts the movement track of the infant according to the acceleration of the infant, predicts whether the infant can enter a dangerous area within preset time, and sends alarm information to the mobile phone terminal through the WIFI module when the target object is predicted to enter the dangerous area within the preset time.
Optionally, the ARM module calculates the acceleration of the infant according to the positioning data of the target object, including the following steps:
the ARM module constructs a baby motion state prediction model according to a Kalman filtering calculation method as follows:
Figure BDA0001707580080000031
Figure BDA0001707580080000032
Figure BDA0001707580080000033
wherein a ismaxIs the target maximum acceleration at which the acceleration is,
Figure BDA0001707580080000034
the method comprises the steps of obtaining an acceleration variance, P (k +1| k) a priori error matrix, F the magnitude of a forward force, h the measured height of the infant, g the gravity acceleration, E (a) selecting and adopting a priori acceleration estimation value, P (k | k) a posterior error matrix, calculating through Kalman gain and a priori error, phi (k +1| k) a prediction matrix of the motion state of the infant, obtaining by analyzing the corresponding relation between ultrasonic data and the motion state of the infant, β a time constant of the acceleration of the infant, and Q (k) a variance matrix of the motion state of the infant.
Optionally, the predicting the motion trail of the child according to the acceleration of the child includes the following steps:
and calculating Kalman gain based on the prior Kalman filtering error matrix, performing posterior Kalman prediction, calculating posterior errors, and finally predicting the target motion track.
The infant high-altitude falling prevention system and method have the advantages that: the invention provides a high-altitude anti-falling scheme for infants based on camera, infrared and ultrasonic data composition, which adopts an infrared night vision camera to capture human faces and acquire human face information and an infrared module to acquire target height; the method comprises the steps of positioning the position of an infant by adopting an ultrasonic module, carrying out data processing on images, height and position information by adopting an ARM module, and predicting the motion trend of a target by utilizing a motion state prediction algorithm of Kalman filtering; and information transmission is carried out by adopting WIFI, and the alarm information is transmitted to the guardian. The system has the advantages of wide detection range, high infant identification rate, low false alarm rate, stable operation, high reliability and the like, meets the basic requirements of the infant high-altitude falling prevention window, and has higher application value.
Drawings
FIG. 1 is a block diagram of an embodiment of the invention of a high-altitude anti-falling system for infants;
FIG. 2 is a schematic diagram of the operation of the high altitude anti-fall system for infants according to one embodiment of the present invention;
FIG. 3 is a flowchart illustrating the operation of the high fall arrest system for infants according to an embodiment of the present invention;
FIG. 4 is a flow chart of a Kalman filtering based infant motion state prediction algorithm according to an embodiment of the present invention;
fig. 5 is a schematic circuit diagram of an OV5647 camera module in accordance with an embodiment of the present invention;
FIG. 6 is a circuit schematic of an infrared module of one embodiment of the present invention;
FIG. 7 is a circuit schematic of an HG-C40UC ultrasonic module of an embodiment of the present invention;
FIGS. 8-10 are schematic circuit diagrams of an ARM module according to an embodiment of the present invention;
figure 11 is a circuit schematic of a GPIO module of one embodiment of the present invention;
FIG. 12 is a schematic circuit diagram of a camera interface module according to an embodiment of the invention;
FIGS. 13a and 13b are circuit schematic diagrams of a power module according to an embodiment of the invention;
figure 14 is a circuit schematic of an alarm module of one embodiment of the present invention.
Detailed Description
In order to more clearly describe the technical contents of the present invention, the following further description is given in conjunction with specific embodiments.
As shown in fig. 1, in order to solve the above technical problems, the invention provides a high-altitude anti-falling system for infants based on camera, infrared and ultrasonic fusion, which comprises a data acquisition subsystem, an ARM control subsystem and a mobile phone terminal. Wherein:
the data acquisition subsystem is composed of a camera module for capturing human faces and acquiring human face information, an infrared human body induction module for measuring the height of a target, an ultrasonic module for positioning the target and the like. The ARM control subsystem mainly comprises a GPIO (General Purpose Input Output) module for reading data of the infrared human body induction module and the ultrasonic module, a camera interface module for reading image data collected by the camera module, an ARM module for data processing, data analysis and control, a WiFi module for communicating with a mobile phone terminal, a window closing brake for closing a window, a power supply module for supplying power, an alarm module for alarming and the like.
The data acquisition subsystem: the camera module is connected with a camera interface module in the ARM control subsystem, and the ultrasonic module and the infrared human body induction module are connected with a GPIO module in the ARM control subsystem. The ARM control subsystem: the camera module, the GPIO module, the window closing brake module, the alarm module, the WiFi module and the power module are all connected with the ARM module. The ARM control subsystem is communicated with the mobile phone terminal through the WiFi module.
And further, the ARM control subsystem predicts the motion trend of the target through a motion state prediction algorithm of Kalman filtering according to the face information, the height and the position acquired by the data acquisition subsystem.
And further, the motion state prediction algorithm of Kalman filtering is used for solving the maximum acceleration of the infant to optimize the traditional Kalman filtering algorithm according to the human body acceleration statistical model, so that the system performance is improved, and the error is reduced.
As shown in fig. 2, the working schematic diagram of the present invention includes that ultrasonic modules 2 are installed at the same horizontal height and distributed in an L shape at positions close to the ground, a window closing brake 3 is installed at a middle position of a lower edge of a window, an infrared module 6 is installed at a position close to the ground vertically below the window closing brake 3, a camera module 5 is installed at a middle position of an upper edge of the window, an alarm module 4 is installed beside the window, a WiFi module 1 is placed on a tea table, the camera module 5 captures a human face and identifies the human face, the infrared module 6 identifies the height of the human body, whether the child is determined by the human face identification and the height identification, if the determined child is the child, the position of the child is positioned by the ultrasonic modules 2 to estimate the motion trajectory of the child, if the estimated result is that the child is likely to be dangerous, information is sent to a mobile phone terminal by the WiFi, and simultaneously activates the window closing brake 3 to close the window.
As shown in fig. 3, which is a flow chart of the infant high-altitude falling prevention system, that is, the flow chart of the infant high-altitude falling prevention method of the present invention, first, data acquisition is performed through a camera, infrared rays, and ultrasonic waves, information such as images, heights, and positioning is obtained, and whether an infant is present is determined. Specifically, the ARM module analyzes the face image data, and determines whether the age of the target object is within a preset age range, where an existing face recognition method can be adopted; the ARM module analyzes the height area of the target object and judges whether the height of the target object is within a preset height range or not; and if the age of the target object is within the preset age range and the height of the target object is within the preset height range, judging that the infant is detected. And predicting the movement track of the infant by using a Kalman filtering algorithm, judging whether the infant enters a dangerous area, and finally judging whether to give an alarm and closing a window according to the degree of danger.
As shown in fig. 4, a flow chart of a kalman filtering-based infant motion state prediction algorithm in the infant high-altitude falling prevention method is provided, and according to a calculation method of the kalman filtering, a infant motion state prediction model is constructed: according to a domestic standard height and weight scale table of the infant and a human kinematics theory, an infant acceleration model is established and solved, and an acceleration variance is optimized to obtain a reasonable prior Kalman filtering error matrix:
Figure BDA0001707580080000051
Figure BDA0001707580080000052
Figure BDA0001707580080000053
wherein a ismaxIs the target maximum acceleration at which the acceleration is,
Figure BDA0001707580080000054
the infant motion state prediction matrix is obtained by analyzing the corresponding relation between ultrasonic wave data and infant motion states, specifically, the matrix is obtained by measuring motion state data (displacement, speed and acceleration) of different moments in the infant motion process and analyzing the corresponding relation between the motion state data of continuous moments, β is an infant acceleration time constant, Q (k) is an infant motion state variance matrix, the variance of the infant motion state data (displacement, speed and acceleration) at different moments is recorded, an initial moment frame is generally set as [0,0,1, [0, 1 ] an]. And calculating Kalman gain through a priori Kalman filtering error matrix, performing posterior Kalman prediction, calculating posterior errors, and finally predicting the target motion track.
As shown in fig. 5, which illustrates a camera module circuit according to an embodiment of the present invention, pins 1, 4, 7, 10, 13, 16, and 19 of the camera module CAM1 are grounded, pin 2 is connected to pin 2 of the camera interface module J4, pin 3 of pin 3J 4, pin 5 of pin 5J 4, pin 6 of pin 6J 4, pin 8 of pin 8J 4, pin 9 of pin 9J 4, pin 17 of pin 17J 4, pin 18 of pin 18J 4, and pin 21 of pin 20J 4. 11. The 12, 14 and 15 feet are suspended.
As shown in fig. 6, which illustrates an infrared module circuit according to an embodiment of the present invention, pin 1 of the infrared module P1 is connected to a 5V power supply, pin 2 is connected to pin 8 of the GPIO module, and pin 3 is connected to ground.
As shown in fig. 7, which illustrates an ultrasonic module circuit according to an embodiment of the present invention, pin 1 of the ultrasonic module H1 is connected to a 5V power supply, pin 2 is connected to ground, pin 3 is connected to pin 29 of the GPIO module, pin 4 is connected to pin 31 of the GPIO module, pin 5 is connected to pin 26 of the GPIO module, pin 6 is connected to pin 19 of the GPIO module, pin 7 is connected to pin 23 of the GPIO module, and pin 8 is suspended.
As shown in fig. 8, an ARM module circuit according to an embodiment of the present invention is shown, in the ARM module, the pin P9 of U1A is connected to the power supply of 1.8V, the pins N7, P7, and N8 of U1A are connected to the pins C2 and C3, the pin R8 of U1A is connected to the pin 3 of the crystal oscillator X1, the pin R9 of U1A is connected to the pin 1 of the crystal oscillator X1, the pin 1 of the capacitor C4 is connected to the pin 1 of the X1, the pin 2 of the capacitor C4 is connected to ground, the pin 1 of the capacitor C5 is connected to the pin 3 of the X1, the pin 2 of the capacitor C5 is connected to ground, the pins 2 and 4 of the crystal oscillator are connected to ground, the pin 1 of the capacitor C1 is connected to the power supply of 1.8V, the pin 2 is connected to ground, and the.
As shown in fig. 9, which illustrates an ARM module circuit according to an embodiment of the present invention, the R14 pin of U2 in the ARM module is connected to a 3.3V power supply, the U1 and U2 pins of U2 are grounded, the P14 pin of U2 is connected to 2 pins of 1005, the 27 pin of U2 is connected to 1 pin of 1005, the 1 pin of 2.54mm socket is connected to 2 pins of 1005, and the 2 pin of 2.54mm socket is connected to ground,
as shown in fig. 10, which illustrates an ARM module circuit according to an embodiment of the present invention, pins H4 and E4 of U3 in the ARM module are connected to a 3.3V power supply, pin J6 of U3 is connected to pin 1 of resistor R1, pin J4 of U3 is connected to pin 1 of resistor R2, and pins R1 and R2 are connected to a 3.3V power supply. The 1 pin of the capacitor C6 is connected with a 3.3V power supply, the 2 pin is connected with the ground, the R10 pin of the CAM0 is connected with a 1.8V power supply, and the T5 pin is connected with the ground.
As shown in fig. 11, which shows the GPIO module circuit according to an embodiment of the present invention, pins 1 and 17 of the GPIO module J1 are connected to a 3.3V power supply, pins 2 and 4 are connected to a 5V power supply, pins 6, 9, 14, 20, 25, 30, 34, and 39 are connected to ground, pin 3 is connected to the J pin of the BCM2838 chip U, pin 5 is connected to the J pin of U, pin 7 is connected to the H pin of U, pin 8 is connected to the D pin of U, pin 10 is connected to the E pin of U, pin 11 is connected to the E pin of U, pin 12 is connected to the B pin of U, pin 15 is connected to the B pin of U, pin 5 is connected to the B pin of U, pin 16 is connected to the C pin of U, pin 18 is connected to the a pin of U, pin 19 is connected to the G pin of U, pin 21 is connected to the G pin of U, pin 22 is connected to the a pin of U, pin 23 is connected to the G pin of U, pin 24 is connected to the F pin of U, pin 26 is connected to the D pin 27, and pin H pin 28 is connected to the H pin of U, the 29 foot is connected with the H3 foot of U3, the 31 foot is connected with the G1 foot of U3, the 32 foot is connected with the H7 foot of U3, the 33 foot is connected with the G5 foot of U3, the 35 foot is connected with the G8 foot of U3, the 36 foot is connected with the C1 foot of U3, the 37 foot is connected with the D6 foot of U3, the 38 foot is connected with the E5 foot of U3, the 40 foot is connected with the C4 foot of U3,
as shown in fig. 12, which illustrates a camera interface module circuit according to an embodiment of the present invention, pins 1, 4, 7, 10, 13, 16, and 19 of the camera interface module J4 are grounded, pin 2 is connected to pin M11 of CAM module CAM0, pin 3 is connected to pin N11 of CAM0, pin 5 is connected to pin M12 of CAM0, pin 6 is connected to pin N12 of CAM0, pin 8 is connected to pin P11 of CAM0, pin 9 is connected to pin R11 of CAM0, pin 20 is connected to pin J6 of CAM0, and pin 21 is connected to pin J4 of CAM0, and pins 11, 12, 14, and 15 are suspended.
As shown in fig. 13, a power module circuit according to an embodiment of the present invention is shown, a pin 1 of an RT1 of the power module is connected to pins 1 of capacitors C14, C17, and C16, a pin 2 of an RT1 is connected to pins 2 of capacitors C14, C17, and C16, a pin 3 of an RT1 is connected to pin 1, a pin 4 of an RT1 is connected to pin 1 of C18, a pin 5 of an RT1 is connected to a 3.3V power supply, capacitors C14, C16, and a pin 2 of a C17 are connected to pin 5V power supply of a resistor BD1, a pin 2 is connected to pin 1 of an RT1, a pin 2 of a capacitor C1 is connected to ground, a pin 1 of a C1 is connected to ground, a pin 2 of a capacitor C1 is connected to 3.3V power supply, a pin 1 of a diode is connected to 3.3V power supply, a pin 1 of a pin R1 of a pin 2 is connected to ground, a pin 1 of a regulator D1, a pin 2V 3.3V power supply, a pin of a power supply socket of a power supply pin 3, a power supply pin P1, a.
As shown in fig. 14, which shows an alarm module circuit according to an embodiment of the present invention, pin 1 of the alarm module JB is connected to a 12V power supply, pin 2 of the JB is connected to pin 8 of the GPIO module, and pin 3 is connected to ground.
In this embodiment, the camera module model number OV 5467; the infrared module is VI-40VIS-60 in model; the ultrasonic module is of a model HG-C40 UA; the model of the ARM module chip is BCM 2835; the power module chip RT1 model RT 9192; the alarm module is JB model LTE-1101J. The invention is only in several optional product models, and it can be understood that the invention can also adopt various functional modules in other models, and can realize corresponding functions, and all of them are within the protection scope of the invention.
The infant high-altitude falling prevention system and method have the advantages that: the invention provides a high-altitude anti-falling scheme for infants based on camera, infrared and ultrasonic data composition, which adopts an infrared night vision camera to capture human faces and acquire human face information and an infrared module to acquire target height; the method comprises the steps of positioning the position of an infant by adopting an ultrasonic module, carrying out data processing on images, height and position information by adopting an ARM module, and predicting the motion trend of a target by utilizing a motion state prediction algorithm of Kalman filtering; and information transmission is carried out by adopting WIFI, and the alarm information is transmitted to the guardian. The system has the advantages of wide detection range, high infant identification rate, low false alarm rate, stable operation, high reliability and the like, meets the basic requirements of the infant high-altitude falling prevention window, and has higher application value.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims (6)

1. The utility model provides an infant prevents system of falling in high altitude which characterized in that, includes data acquisition subsystem, ARM control subsystem and cell-phone terminal, the data acquisition subsystem includes:
the camera module is used for acquiring a face image of a target object;
the infrared human body sensing module is used for measuring the height of a target object;
the ultrasonic module is used for positioning a target object;
the ARM control subsystem comprises:
the GPIO module is used for reading the data of the infrared human body induction module and the data of the ultrasonic wave module;
the camera interface module is used for reading the face image data collected by the camera module;
the WIFI module is used for communicating with the mobile phone terminal;
the ARM module is connected with the GPIO module, the camera interface module and the WIFI module;
the ARM module analyzes the face image data and the height data of the target object to judge whether an infant is detected;
if the infant is detected, the ARM module judges whether the target object enters a dangerous area or not according to the positioning data of the target object, and when the target object enters the dangerous area, the WIFI module sends alarm information to the mobile phone terminal;
the ARM module judges whether the target object enters a dangerous area according to the positioning data of the target object by adopting the following steps:
the ARM module calculates the acceleration of the infant according to the positioning data of the target object, predicts the movement track of the infant according to the acceleration of the infant, predicts whether the infant enters a dangerous area within a preset time, and sends alarm information to the mobile phone terminal through the WIFI module when the target object is predicted to enter the dangerous area within the preset time;
the ARM module calculates the acceleration of the infant according to the positioning data of the target object by adopting the following steps:
the ARM module constructs a baby motion state prediction model according to a Kalman filtering calculation method as follows:
Figure FDA0002391056840000011
Figure FDA0002391056840000012
Figure FDA0002391056840000013
wherein a ismaxIs the target maximum acceleration at which the acceleration is,
Figure FDA0002391056840000021
the method comprises the steps of obtaining an acceleration variance, wherein P (k +1| k) is a priori error matrix, F is the magnitude of the advancing force, h is the measured height of the infant, g is the gravity acceleration, E (a) selects and adopts a priori acceleration estimation value, P (k | k) is a posterior error matrix, the estimation value is obtained through Kalman gain and a priori error calculation, phi (k +1| k) is an infant motion state prediction matrix, β is an infant acceleration time constant, and Q (k) is an infant motion state variance matrix.
2. The infant high altitude anti-falling system according to claim 1, wherein the ARM control subsystem further comprises a window closing brake, the window closing brake is installed at a middle position of a lower edge of the window, and when the ARM module judges that the infant enters a dangerous area, the window is controlled to be closed through the window closing controller.
3. The infant high altitude anti-falling system according to claim 1, wherein the ARM control subsystem further comprises an alarm module, and when the ARM module determines that the infant enters a dangerous area, the alarm module is controlled to give an audible alarm and/or a luminous alarm.
4. A method for preventing falling from high altitude of a child, which comprises the following steps:
the ARM module analyzes the face image data and the height data of the target object to judge whether an infant is detected;
if the infant is detected, the ARM module judges whether the target object enters a dangerous area or not according to the positioning data of the target object, and when the target object enters the dangerous area, the WIFI module sends alarm information to the mobile phone terminal;
the ARM module judges whether the target object enters a dangerous area according to the positioning data of the target object, and the method comprises the following steps:
the ARM module calculates the acceleration of the infant according to the positioning data of the target object, predicts the movement track of the infant according to the acceleration of the infant, predicts whether the infant enters a dangerous area within a preset time, and sends alarm information to the mobile phone terminal through the WIFI module when the target object is predicted to enter the dangerous area within the preset time;
the ARM module calculates the acceleration of the infant according to the positioning data of the target object, and the method comprises the following steps:
the ARM module constructs a baby motion state prediction model according to a Kalman filtering calculation method as follows:
Figure FDA0002391056840000022
Figure FDA0002391056840000023
Figure FDA0002391056840000024
wherein a ismaxIs the target maximum acceleration at which the acceleration is,
Figure FDA0002391056840000025
is the acceleration variance, P (k +1| k) is the prior error matrix, and F is the magnitude of the forward forceH is the measured height of the infant, g is the gravity acceleration, E (a) selects to adopt a priori acceleration estimated value, P (k | k) is a posterior error matrix and is obtained through Kalman gain and a priori error calculation, phi (k +1| k) is an infant motion state prediction matrix, β is an infant acceleration time constant, and Q (k) is an infant motion state variance matrix.
5. The infant high-altitude falling prevention method according to claim 4, wherein the ARM module analyzes the face image data and the height data of the target object to judge whether the infant is detected, and comprises the following steps:
the ARM module analyzes the face image data and judges whether the age of the target object is within a preset age range;
the ARM module analyzes the height area of the target object and judges whether the height of the target object is within a preset height range or not;
and if the age of the target object is within the preset age range and the height of the target object is within the preset height range, judging that the infant is detected.
6. The method for preventing falling aloft of infant as claimed in claim 4, wherein the step of predicting the movement track of infant according to the acceleration of infant comprises the following steps:
and calculating Kalman gain based on the prior Kalman filtering error matrix, performing posterior Kalman prediction, calculating posterior errors, and finally predicting the target motion track.
CN201810665581.9A 2018-06-26 2018-06-26 High-altitude falling prevention system and method for infants Active CN109035685B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810665581.9A CN109035685B (en) 2018-06-26 2018-06-26 High-altitude falling prevention system and method for infants

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810665581.9A CN109035685B (en) 2018-06-26 2018-06-26 High-altitude falling prevention system and method for infants

Publications (2)

Publication Number Publication Date
CN109035685A CN109035685A (en) 2018-12-18
CN109035685B true CN109035685B (en) 2020-06-23

Family

ID=64610453

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810665581.9A Active CN109035685B (en) 2018-06-26 2018-06-26 High-altitude falling prevention system and method for infants

Country Status (1)

Country Link
CN (1) CN109035685B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110084995B (en) * 2019-04-30 2021-12-03 北京百度网讯科技有限公司 Radiation prompting method and device, electronic equipment and storage medium
CN110826406A (en) * 2019-10-08 2020-02-21 赵奕焜 Child high-altitude protection method based on deep learning model
CN111145476A (en) * 2019-12-26 2020-05-12 星络智能科技有限公司 Anti-falling control method for children
CN111568224A (en) * 2020-02-29 2020-08-25 佛山市云米电器科技有限公司 Safe water outlet method of water dispenser, water dispenser and computer readable storage medium
CN112634581B (en) * 2020-12-14 2021-11-23 珠海格力电器股份有限公司 Method and system for prompting falling object danger and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204856830U (en) * 2015-08-31 2015-12-09 余莺 Children prevent reminding device that falls down from building
CN106781266A (en) * 2017-02-23 2017-05-31 黄安攀 A kind of anti-early warning system of falling down from the building of child
CN107015944A (en) * 2017-03-28 2017-08-04 南京理工大学 A kind of mixing square root volume kalman filter method for target following
CN107545701A (en) * 2017-07-31 2018-01-05 昆明理工大学 A kind of child intelligence protector based on pulse
CN107798820A (en) * 2017-09-12 2018-03-13 中山大学 It is a kind of that intelligence system that children fall down from the building is prevented based on Internet of Things

Also Published As

Publication number Publication date
CN109035685A (en) 2018-12-18

Similar Documents

Publication Publication Date Title
CN109035685B (en) High-altitude falling prevention system and method for infants
CN103839373B (en) A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system
US11978256B2 (en) Face concealment detection
CN111279044B (en) Garage door controller and monitor and mode
CN105069976B (en) A kind of fatigue detecting and traveling record integrated system and fatigue detection method
CN103839346A (en) Intelligent door and window anti-intrusion device and system and intelligent door control system
WO2015009951A1 (en) Fall detection using machine learning
US11165954B1 (en) Scene-aware custom tuned video surveillance detection system
AU2018375154B2 (en) Ultrasound analytics for actionable information
CN110826406A (en) Child high-altitude protection method based on deep learning model
US20230196106A1 (en) Training image classifiers
CN114049605A (en) Intelligent monitoring method, equipment and system and storage medium
US11200793B2 (en) Notifications for camera tampering
CN105825631B (en) fatigue detection method and system based on video intelligent algorithm
US11823452B2 (en) Video analytics evaluation
US20220335725A1 (en) Monitoring presence or absence of an object using local region matching
CN108765616A (en) A kind of school student attendance system and method based on recognition of face
US11550276B1 (en) Activity classification based on multi-sensor input
US20210274133A1 (en) Pre-generating video event notifications
CN110300257B (en) Face tracking security monitoring system based on deep learning and use method thereof
US20230360430A1 (en) Face detector using positional prior filtering
US20230110877A1 (en) Camera blindspot analysis
US20210122467A1 (en) Drone navigation and landing
US20220230410A1 (en) Object localization in video
US20230081909A1 (en) Training an object classifier with a known object in images of unknown objects

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant